Performance & Cost, Shown

Every performance and cost figure we publish is either a measurement you can reproduce or a calculation from published prices. This page shows the work. Numbers below were measured on July 24, 2026.

Measured performance

Benchmarked on the reference GPU host (Intel i9-14900KF, RTX 4070 Ti SUPER 16GB) running the default Tier 1 model qwen3.5:9b via Ollama, warm (model resident). Reproduce with python manage.py test_ollama_models --benchmark.

Task Tokens out Throughput Wall time
Classification 7 85.7 tok/s ~0.3 s
Business analytics 1183 85.4 tok/s ~22 s
Code generation 1382 95.5 tok/s ~14 s
Strategic planning 2293 88.0 tok/s ~26 s

A warm classification (a handful of output tokens) returns in ~300 ms; a short ~60-token answer in ~890 ms. Average generation throughput across task types is ~88.6 tok/s.

Honest scope. These are GPU-host numbers. A GPU-less server runs a Tier 1 cloud model (gpt-oss:120b-cloud) whose latency is network-bound and not represented here. Escalated (Tier 2/3) requests to a frontier model are slower than local generation. We publish only what we measured.

The cost model

MythosLab routes by stakes, not raw complexity. The Tier 1 workhorse handles the bulk of work at a flat or zero marginal cost; only the hard or accuracy-critical minority reaches a per-token frontier model. Published list prices (per million tokens):

Tier Model Input Output Share of traffic
1 workhorse qwen3.5:9b / gpt-oss:120b-cloud $0 local / flat $0 local / flat 85-90%
2 general claude-sonnet-5 $3.00 $15.00 5-8%
3 critical claude-opus-5 $5.00 $25.00 2-5%

Worked example. Assume an average request of ~500 input + ~1,000 output tokens, and the tier mix above (88% / 7% / 5%). Every escalated request costs $0.0165 (Sonnet 5) or $0.0275 (Opus 4.8). Two monthly volumes:

Monthly requests Per-token escalation On your own GPU On a GPU-less VPS
5,000 ~$13 ~$13/mo ~$33/mo
10,000 ~$25 ~$25/mo ~$45/mo

The VPS column adds a flat ~$20/mo Ollama Cloud subscription for Tier 1 (a GPU-less box cannot run the local model); the GPU column runs Tier 1 for free on hardware you already own. Embeddings always run locally on CPU at no cost.

What it replaces

Same workload, no tiering. Running those same 10,000 requests entirely on a frontier model instead of tiering costs ~$165/mo (all Sonnet 5) to ~$275/mo (all Opus 4.8) in API charges alone. Tiering cuts that by 60-85% -- the same math, just keeping the routine work off the meter.

Versus per-seat enterprise AI. Hosted enterprise AI assistants are priced per seat: Microsoft 365 Copilot at $30/user/mo on top of a qualifying license (all-in $69-90/seat), ChatGPT Enterprise reported around $45-75/seat with a 150-seat minimum, and enterprise search tools like Glean at $40+/seat plus a platform fee. For a 20-person business that is $600-1,800/month, scaling with headcount. MythosLab's compute cost does not scale per seat -- the figures above cover the whole team.

Bottom line: a 20-seat small business typically spends $15-45/month of AI compute on MythosLab versus $600-1,800/month for per-seat enterprise AI -- while keeping every byte of data on its own infrastructure.

Sources & assumptions

  • Local benchmarks: test_ollama_models --benchmark on the reference host, July 24, 2026. Your throughput varies with hardware and prompt shape.
  • Anthropic list prices are the model rates MythosLab charges cost against in core/inference/anthropic_client.py.
  • Tier shares (85-90% / 5-8% / 2-5%) are routing targets; your real mix depends on your workload and is visible on the in-app analytics dashboard.
  • Enterprise-AI per-seat pricing reflects mid-2026 published/reported rates and is illustrative; exact quotes vary by contract and existing licensing.